CASA uses spectral density to arbitrate between preserving the target model's manifold and restoring LoRA alignment, mitigating style degradation and structural collapse in distilled video diffusion models.
Trans-LoRA: towards data-free Transferable Parameter Efficient Finetuning , volume =
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Exploring Data-Free LoRA Transferability for Video Diffusion Models
CASA uses spectral density to arbitrate between preserving the target model's manifold and restoring LoRA alignment, mitigating style degradation and structural collapse in distilled video diffusion models.